Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    INDEX
    Explanations

    references to practicality or practical applications

    oai_token-act-pair · gpt-3.5-turbo

    references to practical situations or applications

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    adder
    -0.84
    Gate
    -0.77
    velt
    -0.72
    buck
    -0.72
    ramid
    -0.70
    rael
    -0.68
    better
    -0.68
    Torrent
    -0.67
    hips
    -0.66
    holes
    -0.65
    POSITIVE LOGITS
    ity
    0.96
     considerations
    0.89
     impossibility
    0.80
    ities
    0.80
     necessities
    0.75
     embodiment
    0.75
    istically
    0.74
     necessity
    0.73
     practical
    0.73
     relevance
    0.72
    Act Density 0.010%

    No Known Activations